Search

We present a physics informed deep learning technique for Deeply Virtual Compton Scattering (DVCS) cross sections from an unpolarized proton target using both an unpolarized and polarized electron beam. Training a deep learning model typically requires a large size of data that might not always be available or possible to obtain. Alternatively, a deep learning model can be trained using additional knowledge gained by enforcing some physics constraints such as angular symmetries for better accuracy and generalization. By incorporating physics knowledge to our deep learning model, our framework shows precise predictions on the DVCS cross sections and better extrapolation on unseen kinematics compared to the basic deep learning approaches.

The study of the azimuthal anisotropy of final-state particle distribution allows a better understanding of the perfect fluid properties of the Quark-Gluon Plasma (QGP). Using a Toy Monte Carlo generator, we have measured flow coefficient (vn) as a function of the number of events, particle multiplicity and signal strength (vn magnitude) with a 2-particle cumulant technique. This study allows to demonstrate that cumulant technique works down to small particle multiplicities and signal strength. In addition, it is a good tool to predict experimental precision as a function of number of events, particle multiplicity and signal strength